EGAnet (version 1.2.3)

network.descriptives: Descriptive Statistics for Networks

Description

Computes descriptive statistics for network models

Usage

network.descriptives(network)

Value

Numeric vector including:

Mean_weight

The average of the edge weights in the network

SD_weight

The standard deviation of the edge weights in the network

Min_weight

The minimum of the edge weights in the network

Max_weight

The minimum of the edge weights in the network

Density

The density of the network

ASPL

The average shortest path length (ASPL) of the network (computed as unweighted)

CC

The clustering coefficent (CC) of the network (computed as unweighted)

swn.rand

Small-worldness measure based on random networks:

$$swn.rand = (ASPL / ASPL_random) / (CC / CC_random)$$

swn.rand > 1 suggests the network is small-world

swn.HG

Small-worldness measure based on Humphries & Gurney (2008):

$$swn.HG = (transitivity / transitivity_random) / (ASPL / ASPL_random)$$

swn.HG > 1 suggests the network is small-world

swn.TJHBL

Small-worldness measure based on Telesford, Joyce, Hayasaka, Burdette, & Laurienti (2011):

$$swn.TJHBL = (ASPL_random / ASPL) - (CC / CC_lattice)$$

swn.TJHBL near 0 suggests the network is small-world, positive values suggest more random network characteristics, negative values suggest more lattice network characteristics

scale-free_R-sq

The R-squared fit of whether the degree distribution follows the power-law (many small degrees, few large degrees)

Arguments

network

Matrix, data frame, qgraph, or EGA object

Author

Hudson Golino <hfg9s at virginia.edu> and Alexander P. Christensen <[e-mail]>

References

# swn.HG
Humphries, M. D., & Gurney, K. (2008). Network 'small-world-ness': A quantitative method for determining canonical network equivalence. PLoS one, 3, e0002051

# swn.TJHBL
Telesford, Q. K., Joyce, K. E., Hayasaka, S., Burdette, J. H., & Laurienti, P. J. (2011). The ubiquity of small-world networks. Brain Connectivity, 1(5), 367-375

# scale-free_R-sq
Langfelder, P., & Horvath, S. (2008). WGCNA: an R package for weighted correlation network analysis. BMC Bioinformatics, 9, 559

Examples

# Load data
wmt <- wmt2[,7:24]

if (FALSE) # EGA example
ega.wmt <- EGA(data = wmt)

# Compute descriptives
network.descriptives(ega.wmt)